Klasifikasi Kemampuan Berpikir Kreatif Peserta Didik Madrasah Ibtidaiyah Menggunakan Algoritma K-Nearest Neighbor
DOI:
https://doi.org/10.59395/ba06yc73Keywords:
berpikir kreatif, madrasah ibtidaiyah, permasalahan matematis, KNN, clusteringAbstract
Keterampilan berpikir kreatif adalah salah satu keterampilan abad ke-21 yang signifikan bagi siswa sekolah dasar, termasuk Madrasah Ibtidaiyah. Namun, guru mengajar matematika masih memiliki motivasi yang kurang efisien pada materi yang lebih komprehensif dalam menyelesaikan permasalahan matematis dengan jawaban tunggal dan metode tradisional. Hal ini berimplikasi bahwa siswa kurang didorong untuk mengahsilafkan ide yang bervariasi dan orisinil. Oleh karena itu, penelitian ini menganalisis keterampilan berpikir kreatif dalam soal cerita matematika dengan menggunakan pendekatan analisis data K-Nearest Neighbor (KNN). Penelitian ini menggunakan desain kuantitatif dan deskriptif. Subjek penelitian dinilai menggunakan instrumen berdasarkan indikator keterampilan berpikir kreatif: kelancaran (fluency), keluwesan (flexibility), keaslian (originality), dan elaborasi (elaboration). Hasil kerja siswa kemudian diklasifikasikan ke dalam tingkat keterampilan berpikir kreatif (tinggi, sedang, rendah) menggunakan algoritma KNN.). Berdasarkan hasil analisis, sebagian besar siswa tergolong dalam kategori keterampilan berpikir kreatif sedang, sedangkan kategori tinggi dan rendah hanya mencakup sebagian kecil siswa. Algoritma KNN menunjukkan kemampuan klasifikasi yang efektif dengan tingkat akurasi melebihi 80%. Temuan ini menguatkan perlunya integrasi teknologi analisis data yang sederhana dalam konteks pendidikan dasar, sekaligus menjadi pertimbangan bagi pendidik dalam merancang pembelajaran matematika yang lebih adaptif, kreatif, dan responsif terhadap tingkat kemampuan siswa.
Downloads
References
[1] Li, Y. et al. (2025). Applying Machine Learning to Intelligent Assessment of Scientific Creativity. Springer.
[2] Cetinkaya, A., Baykan, Ö.K., & Kırgız, H. (2023). Analysis of Machine Learning Classification Approaches for Predicting Students' Programming Aptitude. Sustainability.
[3] Luo, W. et al. (2025). Forms and Functions Innovation in Early Childhood Education Practice. Springer.
[4] Huang, J. et al. (2025). Machine Learning in Educational Process Data. Education Sciences.
[5] Lopez-Bernal, D. et al. (2021). Education 4.0: Teaching the Basics of KNN and LDA Algorithms. Future Internet.
[6] Penuela, D. et al. (2025). AI and Logical Thinking in Primary Education. Advances in Information Systems.
[7] Ferawati, F. et al. (2025). Classification of Children's Numerical Intelligence Levels Using Machine Learning. bit-Tech Journal.
[8] Rismayani, R. et al. (2025). Learning Difficulty Levels Prediction of Elementary Students Using Machine Learning. Jurnal Teknologi Informasi.
[9] Aydın, M. & Yurdugül, H. (2024). Developing a Curriculum Framework of Artificial Intelligence Teaching for Gifted Students. Kastamonu Education Journal.
[10] Castillo-Salazar, D. et al. (2025). Application of Machine Learning for Logical-Mathematical Thinking in Basic Education. Springer.
[11] Chen, S. et al. (2024). Fostering Educational Innovation via KNN Models. BMC Psychology.
[12] Alé, J., Ávalos, B., & Araya, R. (2025). Scientific Practices for Understanding Artificial Intelligence in K-12 Education. Review of Education.
[13] Xin, Y.P. & Chang, H.H. (2025). Application of Machine Learning to Educational Process Data Analysis. Education Sciences.
[14] Lopez-Bernal, D. et al. (2021). Education 4.0 Framework for Computational Thinking. Future Internet.
[15] Li, Y. et al. (2025). AI-Based Scientific Creativity Assessment. Journal of Science Education and Technology.
[16] Fitria, N., Jupri, A., Dahlan, J. A., & Yulianti, K. (2024). Analyzing computational thinking skills in 7th grade students: A focus on data processing in mathematics education. Jurnal Pendidikan Matematika dan Sains
[17] Maylawati, D. S., Mulyana, R., & Rizqullah, N. (2025). Assessing Indonesian Islamic schools' readiness for the independent curriculum using text analytics. Multidisciplinary Research Journal.
[18] Suharto, R., & Nugroho, S. (2023). Application of K-Nearest Neighbor algorithm in classifying students’ learning outcomes in elementary mathematics. Procedia Computer Science.
[19] Putri, M. A., & Santoso, H. (2022). Data mining approach for identifying students’ critical and creative thinking skills in primary education. International Journal of Educational Technology.
[20] Rahman, A., & Lestari, D. (2021). Implementation of K-Nearest Neighbor for student achievement classification in elementary schools. Journal of Physics: Conference Series. IOP Publishing.
[21] Hidayat, R., & Ramadhani, F. (2020). Exploring students’ creative thinking in mathematics through data-driven classification methods. Journal of Educational Research and Evaluation.
[22] Han, J., Kamber, M., & Pei, J. (2022). Data Mining: Concepts and Techniques (4th ed.). Morgan Kaufmann.
[23] Hair, J. F., Black, W. C., Babin, B. J., & Anderson, R. E. (2021). Multivariate Data Analysis (8th ed.). Pearson Education Limited.
[24] Guo, Y., Zhang, H., Li, X., & Chen, L. (2024). An enhanced K-Nearest Neighbor algorithm for educational data classification and student performance prediction. Journal of Educational Data Mining, 16(2), 45–58.
[25] Astutik, S., & Nursyahida, I. (2022). Analisis kemampuan berpikir kreatif siswa sekolah dasar dalam pembelajaran matematika berbasis masalah. Jurnal Pendidikan Dasar Nusantara, 7(1), 33–42.
[26] Zhang, Y., Liu, H., & Wang, X. (2023). Improving student performance classification using K-Nearest Neighbor algorithm with cross-validation and feature scaling techniques. International Journal of Artificial Intelligence in Education, 33(2), 145–160.
Downloads
Published
Issue
Section
License
Copyright (c) 2025 Joko Suprianto, Riezky Army Riesha
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.